Python socket如何解析HTTP请求内容

socket解析HTTP请求内容

思路

1. 解析HTTP请求的头部

HTTP请求头部的结束符行为"\r\n"，可以按行读取HTTP请求头的内容，如果读到一行为"\r\n"，说明HTTP请求头结束。

2. 请求头里面含有Content-Length参数

如果HTTP请求里面有Content-Length参数，说明HTTP请求的内容大小是确定的，请求直接读取Content-Length的值，然后读取相应字节的的内容即可。

3. 请求头里面含有Transfer-Encoding: chunked 参数

如果HTTP请求里面有Transfer-Encoding参数，说明HTTP请求的内容大小是不确定的，这种内容的结束符是"0\r\n\r\n"，因此可以按行读取HTTP请求的内容部分，如果连续读到"0\r\n"和"\r\n"说明内容读取完毕。

代码实现

代码中： self._file 代表的是socket.makefile()

 def get_http_content(self):
        content_length = 0
        transfer_encoding = False
        while True:
            req_line = self._file.readline()
            req_line = str(req_line, "utf-8")
 
            # 遇到http头结束符
            # 读取http内容
            if req_line == "\r\n":
                if content_length != 0:
                    content = self._file.read(content_length)
                    content = str(content, "utf-8")
                    self._content = content
                    return None
 
                if transfer_encoding:
                    content = ""
                    self._file.readline()
                    while True:
                        line = self._file.readline()
                        line = str(line, "utf-8")
                        if line == "0\r\n":
                            sub_line = self._file.readline()
                            sub_line = str(sub_line, "utf-8")
                            if sub_line == "\r\n":
                                self._content = content
                                return None
                        else:
                            content += line
                            continue
                    self._content = False
 
            # 头文件没有结束
            # 并且没有找到关于内容大小的字段
            else:
                if content_length == 0 and transfer_encoding is False:
                    words = req_line.split()
                    if words[0] == "Content-Length:":
                        content_length = int(words[1])
                    if words[0] == "Transfer-Encoding:":
                        transfer_encoding = True
 
            self._content = False

socket 模拟http请求

# coding: utf-8
import socket
from urllib.parse import urlparse
def get_url(url):
    url = urlparse(url)
    host = url.netloc
    path = url.path
    if path == "":
        path = "/"
    # 建立 socket 连接
    client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    client.connect((host, 80))
    client.send("GET {} HTTP/1.1\r\nHost:{}\r\nConnection:close\r\n\r\n".format(path, host).encode("utf-8"))
    data = b""
    while True:
        d = client.recv(1024)
        if d:
            data += d
        else:
            break
    data = data.decode("utf-8")
    html_data = data.split("\r\n\r\n")[1]
    print(html_data)
    client.close()
    pass
if __name__ == '__main__':
    get_url("http://www.baidu.com")

频道导航